• Journal of Korea Multimedia Society
• /
• v.23 no.8
• /
• pp.915-926
• /
• 2020

Outlier detection methods help one to identify unusual instances in data that may correspond to erroneous, exceptional, or surprising events or behaviors. This work studies conditional outlier detection, a special instance of the outlier detection problem, in the context of incorrect data label identification. Unlike conventional (unconditional) outlier detection methods that seek abnormalities across all data attributes, conditional outlier detection assumes data are given in pairs of input (condition) and output (response or label). Accordingly, the goal of conditional outlier detection is to identify incorrect or unusual output assignments considering their input as condition. As a solution to conditional outlier detection, this paper proposes the ratio-based outlier scoring (ROS) approach and its variant. The propose solutions work by adopting conventional outlier scores and are able to apply them to identify conditional outliers in data. Experiments on synthetic and real-world image datasets are conducted to demonstrate the benefits and advantages of the proposed approaches.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.373-376
• /
• 2013

Nowadays, eyes detection is required and considered as the most important step in several applications, such as eye tracking, face identification and recognition, facial expression analysis and iris detection. This paper presents the eyes detection in facial images using Harris corner detection. Firstly, Haar-like features for face detection is used to detect a face region in an image. To separate the region of the eyes from a whole face region, the projection function is applied in this paper. At the last step, Harris corner detection is used to detect the eyes location. In experimental results, the eyes location on both grayscale and color facial images were detected accurately and effectively.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.856-859
• /
• 1997

In this paper we treat the application of fault detection method in DC motor having both model mismatch and noise problems. A fault detection method presented by Kwon et al. (1994) for SISO systems has been here experimented. The model mismatch includes here linearization error as well as undermodelling. Comparisons are made with the real plant, DC motor. The experimental result of robust fault detection method is shown to have good performance via with the alternative fault detection method which do not account noise.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.4
• /
• pp.321-327
• /
• 2012

This paper presents a comparative analysis on three different types of performance indices of obstacle detection for an overlapped ultrasonic sensor ring. Due to beam overlap, the entire sensing zone of each ultrasonic sensor can be divided into three smaller sensing subzones, which leads to significant reduction of positional uncertainty in obstacle detection. First, the positional uncertainty in obstacle detection is expressed in terms of the area of a sensing subzone, and type 1 performance index is then defined as the area ratio of side and center sensing subzones. Second, based on the area of a sensing subzone, type 2 performance index is defined taking into account the size of the entire range of obstacle detection as well as the degree of the positional uncertainty in obstacle detection. Third, the positional uncertainty in obstacle detection is now expressed in terms of the length of the uncertainty arc spanning a sensing subzone, and type 3 performance index is then defined as the average value of the uncertainty arc lengths over the entire range of obstacle detection. Fourth, using a commercial low directivity ultrasonic sensor, the changes of three different performance indices depending on the parameter of an overlapped ultrasonic sensor ring are examined and compared.

• Journal of the Semiconductor & Display Technology
• /
• v.17 no.1
• /
• pp.54-61
• /
• 2018

In this study, two aspects were analyzed about the robot for removal of explosive devices. First, the cost analyses were performed to provide a reasonable solution for the acquirement of the system. It is processed by an engineering estimate method and the process was consisted of two ways : a system development expense and a mass production unit price. In additions, the resultant cost analyses were compared between the cases excluding and including a mines detection system. As results, in the case of the acquirement of the robot system for removal of explosive devices, it is recommended that the performance by improving the mines detection ability should be considered preferentially rather than the cost because the material cost for the mines detection system is negligible compared to the whole system cost. Second, as a way for improving the system performance by the mine detection function, the carbon nanotube (CNT) based sensor technology was studied in terms of sensitivity and simple productivity with presenting its preliminary experimental results. The detection electrodes were formed by a photolithography method using a photosensitive CNT paste. As results, this method was shown as a scalable and expandable technology for the excellent mines detection sensors.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.141-151
• /
• 2022

In recent years, the industry and research communities have focused on developing autonomous crack inspection approaches, which mainly include image acquisition and crack detection. In these approaches, mobile devices such as cameras, drones or smartphones are utilized as sensing platforms to acquire structural images, and the deep learning (DL)-based methods are being developed as important crack detection approaches. However, the process of image acquisition and collection is time-consuming, which delays the inspection. Also, the present mobile devices such as smartphones can be not only a sensing platform but also a computing platform that can be embedded with deep neural networks (DNNs) to conduct on-site crack detection. Due to the limited computing resources of mobile devices, the size of the DNNs should be reduced to improve the computational efficiency. In this study, an architecture called pruned crack recognition network (PCR-Net) was developed for the detection of structural cracks. A dataset containing 11000 images was established based on the raw images from bridge inspections. A pruning method was introduced to reduce the size of the base architecture for the optimization of the model size. Comparative studies were conducted with image processing techniques (IPTs) and other DNNs for the evaluation of the performance of the proposed PCR-Net. Furthermore, a modularly designed framework that integrated the PCR-Net was developed to realize a DL-based crack detection application for smartphones. Finally, on-site crack detection experiments were carried out to validate the performance of the developed system of smartphone-based detection of structural cracks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.5
• /
• pp.2156-2170
• /
• 2020

This paper presents a fire detection algorithm with a minimal false detection rate, intended for a thermal imaging surveillance environment, whose properties vary depending on temporal conditions of day or night and environmental changes. This algorithm was designed to minimize the false detection alarm rate while ensuring a high detection rate, as required in fire detection applications. It was necessary to reduce false fire detections due to non-flame elements occurring when existing fixed threshold-based fire detection methods were applied. To this end, adaptive flame thresholds that varied depending on the characteristics of input images, as well as the center of gravity of the heat-source and hot-source regions, were analyzed in an attempt to minimize such non-flame elements in the phase of selecting flame candidate blocks. Also, to remove any false detection elements caused by camera shaking, one of the most frequently raised issues at outdoor sites, preliminary decision thresholds were adaptively set to the motion pixel ratio of input images to maximize the accuracy of the preliminary decision. Finally, in addition to the preliminary decision results, the texture correlation and intensity of the flame candidate blocks were averaged for a specific period of time and tested for their conformity with the fire decision conditions before making the final decision. To verify the fire detection performance of the proposed algorithm, a total of ten test videos were subjected to computer simulation. As a result, the fire detection accuracy of the proposed algorithm was determined to be 94.24%, with minimum false detection, demonstrating its improved performance and practicality compared to previous fixed threshold-based algorithms.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.4
• /
• pp.682-691
• /
• 2017

In this paper, we propose the fusion design methodology of both pedestrian detection and object tracking system realized with the aid of HOG-PCA based RBFNN pattern classifier. The proposed system includes detection and tracking parts. In the detection part, HOG features are extracted from input images for pedestrian detection. Dimension reduction is also dealt with in order to improve detection performance as well as processing speed by using PCA which is known as a typical dimension reduction method. The reduced features can be used as the input of the FCM-based RBFNNs pattern classifier to carry out the pedestrian detection. FCM-based RBFNNs pattern classifier consists of condition, conclusion, and inference parts. FCM clustering algorithm is used as the activation function of hidden layer. In the conclusion part of network, polynomial functions such as constant, linear, quadratic and modified quadratic are regarded as connection weights and their coefficients of polynomial function are estimated by LSE-based learning. In the tracking part, object tracking algorithms such as mean shift(MS) and cam shift(CS) leads to trace one of the pedestrian candidates nominated in the detection part. Finally, INRIA person database is used in order to evaluate the performance of the pedestrian detection of the proposed system while MIT pedestrian video as well as indoor and outdoor videos obtained from IC&CI laboratory in Suwon University are exploited to evaluate the performance of tracking.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.76-85
• /
• 2019

We introduce a vision-based object detection method for real-time video surveillance system in low-end edge computing environments. Recently, the accuracy of object detection has been improved due to the performance of approaches based on deep learning algorithm such as Region Convolutional Neural Network(R-CNN) which has two stage for inferencing. On the other hand, one stage detection algorithms such as single-shot detection (SSD) and you only look once (YOLO) have been developed at the expense of some accuracy and can be used for real-time systems. However, high-performance hardware such as General-Purpose computing on Graphics Processing Unit(GPGPU) is required to still achieve excellent object detection performance and speed. To address hardware requirement that is burdensome to low-end edge computing environments, We propose sub-frame analysis method for the object detection. In specific, We divide a whole image frame into smaller ones then inference them on Convolutional Neural Network (CNN) based image detection network, which is much faster than conventional network designed forfull frame image. We reduced its computationalrequirementsignificantly without losing throughput and object detection accuracy with the proposed method.

• Journal of Ocean Engineering and Technology
• /
• v.8 no.1
• /
• pp.62-70
• /
• 1994

In order to estimate the detection range of a active SONAR system, the SONAR equation is commonly used. In this paper, an algorithm to calculate detection range in active SONAR system as function of SONAR depth and target depth is presented. For given SONAR parameters and environment, the transmission loss and background level are found, signal excess is computed. Using log-normal distribution, signal excess is converted to detection probability at each range. Then, the detection range is obtained by integrating the detection probability as function of range for each depth. The proposed algorithm have been applied to the case of omni-directional source with center frequency 30Hz for summer and winter sound profiles. It is found that the optimal search depth is the source depth since the detection range increase at source depth where the signal excess is maximized.